UC Berkeley researchers have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence.
They demonstrated their technique, a type of reinforcement learning, by having a robot complete various tasks — putting a clothes hanger on a rack, assembling a toy plane, screwing a cap on a water bottle, and more — without pre-programmed details about its surroundings.
“What we’re reporting on here is a new approach to empowering a robot to learn,” said Professor Pieter Abbeel of UC Berkeley’s Department of Electrical Engineering and Computer Sciences. “The key is that when a robot is faced with something new, we won’t have to reprogram it. The exact same software, which encodes how the robot can learn, was used to allow the robot to learn all the different tasks we gave it.”
The latest developments will be presented on Thursday, May 28, in Seattle at the International Conference on Robotics and Automation (ICRA). Abbeel is leading the project with fellow UC Berkeley faculty member Trevor Darrell, director of the Berkeley Vision and Learning Center. Other members of the research team are postdoctoral researcher Sergey Levine and Ph.D. student Chelsea Finn.
The work is part of a new People and Robots Initiative at UC’s Center for Information Technology Research in the Interest of Society (CITRIS). The new multi-campus, multidisciplinary research initiative seeks to keep the dizzying advances in artificial intelligence, robotics and automation aligned to human needs.
“Most robotic applications are in controlled environments where objects are in predictable positions,” said Darrell. “The challenge of putting robots into real-life settings, like homes or offices, is that those environments are constantly changing. The robot must be able to perceive and adapt to its surroundings.”
Conventional, but impractical, approaches to helping a robot make its way through a 3D world include pre-programming it to handle the vast range of possible scenarios or creating simulated environments within which the robot operates.
Instead, the UC Berkeley researchers turned to a new branch of artificial intelligence known as deep learning, which is loosely inspired by the neural circuitry of the human brain when it perceives and interacts with the world.
“For all our versatility, humans are not born with a repertoire of behaviors that can be deployed like a Swiss army knife, and we do not need to be programmed,” said Levine. “Instead, we learn new skills over the course of our life from experience and from other humans. This learning process is so deeply rooted in our nervous system, that we cannot even communicate to another person precisely how the resulting skill should be executed. We can at best hope to offer pointers and guidance as they learn it on their own.”
In the world of artificial intelligence, deep learning programs create “neural nets” in which layers of artificial neurons process overlapping raw sensory data, whether it be sound waves or image pixels. This helps the robot recognize patterns and categories among the data it is receiving. People who use Siri on their iPhones, Google’s speech-to-text program or Google Street View might already have benefited from the significant advances deep learning has provided in speech and vision recognition.
Applying deep reinforcement learning to motor tasks has been far more challenging, however, since the task goes beyond the passive recognition of images and sounds.
“Moving about in an unstructured 3D environment is a whole different ballgame,” said Finn. “There are no labeled directions, no examples of how to solve the problem in advance. There are no examples of the correct solution like one would have in speech and vision recognition programs.”
The Latest on: Deep Learning
via Google News
The Latest on: Deep Learning
- Semantics of the Black-Box: Can Knowledge Graphs Help Make Deep Learning Systems More Interpretable and Explainable?on February 28, 2021 at 12:03 am
The recent series of innovations in deep learning (DL) have shown enormous potential to impact individuals and society, both positively and negatively. DL models utilizing massive computing power and ...
- Predicts the onset of Alzheimer's Disease (AD) using deep learning-based Splice-AIon February 26, 2021 at 9:02 pm
This study reported for the first time, which identified the gene mutations and abnormal splicing of PLCg1 gene in AD using both high-throughput screening data and a deep learning-based prediction (Sp ...
- Deep Learning Market Share, Development by Companies Outlook, Growth Prospects and Key Opportunities by 2030on February 26, 2021 at 8:51 am
The Deep Learning Market Share is expected to exceed more than US$ 18 Billion by 2024 at a CAGR of 42% in the given ...
- Improved protein structure refinement guided by deep learning based accuracy estimationon February 26, 2021 at 2:52 am
Here the authors present DeepAccNet, a deep learning framework that estimates per-residue accuracy and residue-residue distance signed error in protein models, which are used to guide Rosetta protein ...
- DeepCube’s suite of products drives enterprise adoption of deep learningon February 25, 2021 at 7:01 pm
DeepCube offerings enable up to 10x boost for deep learning deployments on intelligent edge devices and in data centers.
- Deep learning market is expected to grow at a CAGR of around 51.1% over the forecast period 2019 to 2026on February 25, 2021 at 4:03 pm
The global deep learning market is expected to grow at a CAGR of around 51.1% over the forecast period 2019 to 2026 and reach the market value of over US$ 56,427.2 million by 2026. North America held ...
- Interested In AI? Master Deep Learning & Get NLP Certifiedon February 24, 2021 at 9:21 am
The world of artificial intelligence (AI) is revolutionizing the way we live, though it has become something of an acronym soup. From DL to ML, SSD to CN ...
- 3-D holographic microscopy powered by deep-learning deciphers cancer immunotherapyon February 24, 2021 at 7:35 am
Live tracking and analyzing of the dynamics of chimeric antigen receptor (CAR) T-cells targeting cancer cells can open new avenues for the development of cancer immunotherapy. However, imaging via ...
- DeepCube Launches Product Suite to Accelerate Enterprise Adoption of Deep Learningon February 24, 2021 at 6:08 am
DeepCube, the award-winning deep learning pioneer, today announced the launch of a new suite of products and services to help drive enterprise adoption of deep learning, at scale, on intelligent edge ...
- Development of a deep learning-based software for calculating cleansing score in small bowel capsule endoscopyon February 24, 2021 at 3:19 am
A standardized small bowel (SB) cleansing scale is currently not available. The aim of this study was to develop an automated calculation software for SB cleansing score using deep learning.
via Bing News